CHORTLE
Your Friendly SQL Agent
I want to play around with a SQL agent that can be installed in any platform.
Chortle is a multi-tenant Natural Language to SQL (NL2SQL) platform that allows non-technical users to query databases using plain English. It’s designed as a B2B SaaS product where organizations can connect their own databases and enable their teams to get data insights without writing SQL.
Project Highlights:
- I have 8 services powering this:
- API Gatway - Single entry point for auth/rate-limiting. Keeps security concerns separate. MY FAVORITE LAYER!
- Agent Orchestrator - Uses LangGraph to orchestrate the workflow: - Fetch schema → Fetch examples → Generate SQL → Execute → Handle errors (retry up to 3x)
- Schema Registry - The LLM needs to know table/column names to write SQL. This service formats schema metadata into prompts.
- Query Executor - Security isolation. Only allows SELECT, enforces timeouts and row limits. Never runs DELETE/UPDATE.
- LLM Provider - Swap LLM providers without changing other services.
- InHouse LLM Model Service
- Vector Store - RAG pattern. Stores example questions + their SQL so similar questions get better results
- Tenant MAnager - Store tenant databases, API keys, and query history and collects all interactions between services and stores them.
Technologies:
- Python
- Docker
- Node
- ChromaDB
- FastAPI
- Fastify
- LangGraph
- LangChain
